INDEX

Explanations

references to storage solutions and containers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ponge

-0.15

annis

-0.14

acebook

-0.14

 sple

-0.14

 Cage

-0.14

_sess

-0.13

æ¹

-0.13

 uphol

-0.13

/entities

-0.13

eks

-0.13

POSITIVE LOGITS

bag

0.34

Zip

0.33

 bags

0.33

zip

0.33

Zip

0.30

(zip

0.29

 Bags

0.28

Bag

0.28

zip

0.28

 plastic

0.27

Activations Density 0.056%

references to storage solutions and containers

No Comments

No Known Activations